76 results about "Gradient estimation" patented technology

The invention discloses a control method of a flat wire motor. The method comprises the following steps: constructing an optimal current instruction table taking a rotating speed and a torque as indexes; if the motor is in the dynamic working condition, directly looking up a table to obtain a current optimal current instruction; if in a steady-state working condition, performing online search by taking a table look-up result as an initial point: generating two-dimensional Bernoulli random disturbance, and sequentially applying positive and negative disturbances to the initial point; respectively measuring the input power under the two disturbances; according to the ratio of the positive and negative input power difference to the corresponding disturbance component, synchronously calculating gradient estimation vectors of the system input power to d-axis and q-axis current; according to a steepest descent method, the current instruction is updated in the reverse direction of the gradient, an optimal instruction enabling the input power to be minimized is obtained, and an inverter is driven to control a motor to operate. According to the method, through a hybrid control strategy combining dynamic table look-up and steady-state online search, the total loss minimization of the flat wire motor under all working conditions in consideration of alternating current copper loss is realized, and the rapidity of dynamic response is ensured.

The invention relates to the field of generative artificial intelligence image processing, and provides an initial noise distribution optimization method, device, equipment, medium and program, and the method comprises the steps: taking a denoising process as a fixed mapping relation, creating a trainable distribution parameter, and constructing a distribution parameter updating formula based on the fixed mapping relation; constructing a dynamic reward calibration module, calculating a difference value between a reward value of a current initial noise distribution generated image and a reward value of an original standard normal distribution generated image after the diffusion model outputs the generated image every time, and taking the difference value as a relative reward value; constraining the updating process of the distribution parameters by adopting a proportional clipping algorithm; and calculating a parameter updating step length based on a gradient estimation result, and carrying out proportional clipping on the updating step length. The method is used for improving the consistency of content and prompt semantics in a text-to-image generation task by optimizing the initial distribution parameters of the diffusion model, and meanwhile, the generation quality and the calculation efficiency are kept.

The invention discloses a fine tuning system of a large-scale pre-training model in a federated learning environment and application thereof. The system comprises a local disturbance gradient estimation module, a differential privacy protection module and a global model aggregation and update module. The local disturbance gradient estimation module is used for calculating a global model loss value by combining forward propagation with a zero-order optimization method so as to estimate a gradient and realize all-parameter fine tuning; the differential privacy protection module performs differential privacy protection processing on the estimated disturbance gradient to prevent gradient information from leaking user sensitive data; and the global model aggregation and update module reconstructs a disturbance vector and completes global model update based on a random seed and a scalar gradient uploaded by a client. Compared with the prior art, on the premise of not depending on back propagation, all-parameter fine tuning of a large-scale pre-training model is achieved, data privacy is guaranteed, meanwhile, calculation and memory expenses are remarkably reduced, and the method is suitable for a resource-limited distributed calculation environment.

A road surface gradient estimation device includes an acquisition unit that acquires each of detection results of an acceleration detection unit that detects an acceleration in a front-rear direction of a vehicle, and a wheel speed detection unit, and acquires information regarding power for driving the vehicle, a derivation unit that derives a gradient of a road surface on which the vehicle is traveling as a first road surface gradient based on the acquired acceleration and wheel speed, and a correction unit that corrects the derived first road surface gradient based on the information regarding the power for driving the vehicle to derive a second road surface gradient.

A system, method, and computer program product for training a generative language model (GLM) is provided. A plurality of sampled rationales for various question-answer pairs are generated using the GLM. A gradient estimate of parameters of neurons in the GLM is determined based on these sampled rationales to maximize the learning objective of the GLM. The parameters of the GLM are modified using the gradient estimate over multiple iterations, ultimately providing a trained GLM.

To reduce the processing load required to recognize the external environment surrounding the vehicle. [Solution] The external environment recognition device 50 includes an on-board detector 5, a recognition unit 111 that recognizes the road surface and three-dimensional objects on the road on which the vehicle is traveling as road surface information based on point cloud data for each frame acquired by the on-board detector 5, a determination unit 113 that determines the interval of detection points necessary for the point cloud data of the next frame based on the size of a predetermined three-dimensional object set in advance as a recognition target and the measured distance from the vehicle to the three-dimensional object based on the point cloud data, and a gradient prediction unit 114 that predicts the gradient of the road surface not recognized by the recognition unit 111 based on gradient information associated with map information on which the road is recorded. The determination unit 113 further determines the interval of detection points necessary for the point cloud data of the next frame based on the size of a predetermined three-dimensional object, the map information and the estimated distance from the vehicle to the three-dimensional object estimated from the gradient, for a range from the furthest distance to the required distance.

The application discloses a black box optimization gradient estimation method and device based on Rung-Kutta extrapolation and a medium, the method of which comprises the following steps: obtaining a target function to be optimized and a gradient solving reference point corresponding to the target function; configuring gradient calculation related parameters, generating a multi-scale step set and a unit orthogonal perturbation vector set based on the gradient calculation related parameters; determining perturbation positions of the target function under different steps based on the gradient solving reference point, the multi-scale step set and the unit orthogonal perturbation vector set, and converting response data corresponding to each perturbation position into numerical differential data; weighting and fusing the numerical differential data corresponding to different scale steps based on a preset fusion weight; then performing correlation processing on each unit orthogonal perturbation vector to obtain multiple gradient components, and obtaining a final gradient estimation result after aggregation processing of each gradient component. According to the application, the Rung-Kutta extrapolation technology is used to systematically offset low-order truncation errors, and the gradient estimation precision is significantly improved.

The invention relates to an automatic focus following method for a microscope, relates to the technical field of microscope imaging, and aims to construct a defocus distance prediction model by taking focusing as a regression problem so as to directly predict a defocus distance based on a picture. In the initial stage of focusing search, a gradient estimation algorithm without global scanning is provided based on a defocus distance prediction model, and the optimal focal plane is quickly converged through the adjustment steps of detecting a current area, predicting a focusing position, jumping to the focusing position and using the least imaging times and the least camera height, so that the focusing time is remarkably shortened, and the focusing efficiency is improved. The technical problems that an existing focusing algorithm is large in operand, and focusing to a wrong position is prone to occurring are solved.

This application belongs to the field of visual compensation technology and provides a visual compensation method under starlight conditions. Through pre-sampling and grayscale variance statistics, it achieves the determination of starlight compensation intervals and the dynamic division of target and background regions in the imaging plane. It adopts a sampling method with different exposure time series for the target and background regions to obtain multiple frames of original sampled data and pixel integration time. Based on the pixel integration time, it constructs a spatially variable gain matrix and completes inter-frame registration and gain normalization processing to separate signal and noise components in the image. The signal component is used as a sparse sampling stream, and the pixel variance distribution of the noise component is used as a hyperparameter of the variational inference algorithm. Image reconstruction is completed through probability density gradient estimation, making the variational inference process match the actual noise distribution characteristics under starlight conditions, thereby improving the quality and reliability of visual imaging under starlight conditions.

The application discloses a kind of federal reinforcement learning method and system based on hessian auxiliary and strategy gradient under heterogeneous environment, including server and multiple clients, server initializes global model parameter, global gradient update quantity and global control variable and broadcasts to client, client takes current global model parameter as local update starting point, obtains main trajectory and hessian estimation auxiliary trajectory by parameter interpolation and double trajectory sampling, constructs hessian auxiliary correction term at interpolation parameter, and forms local gradient estimation in combination with control variable correction term, uploads parameter update quantity and control variable update quantity after completing multi-step local update, server aggregates each client upload result, updates global model parameter and global control variable, and outputs global strategy model parameter after cyclic iteration, completes federal reinforcement learning.The application can weaken the client drift caused by heterogeneous environment, reduce strategy gradient estimation fluctuation, improve training stability and global strategy performance.

A quantum circuit is configured to implement a quantum gradient algorithm when executed on qubits of a quantum computing system. The quantum gradient algorithm includes a phase oracleOSfmdefined by a finite difference approximation with an order greater than zero, and a complexity of the quantum gradient algorithm scales as (√{square root over (k)} / ϵ). The quantum circuit is repeatedly executed on qubits of a quantum computing system to determine a k-dimensional gradient of a function ƒ(x) within an error ϵ at point x0, where ƒ(x) is not a Gevrey class G1 / 2 function.

The application provides a terahertz SAR high-efficiency self-focusing imaging method and system based on RB-PCA, comprising: obtaining original echo signal data and performing pretreatment; performing distance block in the distance direction on the pretreated echo signal data to obtain a plurality of distance blocks, performing sub-aperture segmentation in the distance block for each distance block to obtain a plurality of sub-aperture signal data; performing desquamation processing on each sub-aperture signal data to obtain desquamation signal data; performing PCA processing on the desquamation signal data and selecting a characteristic vector with the largest characteristic value as a target characteristic vector; obtaining each sub-aperture phase error gradient estimation value through adaptive PGA estimation on the target characteristic vector; obtaining two-dimensional space-varying phase errors of each distance block through global splicing and fusion on each sub-aperture phase error gradient estimation value; and performing phase compensation and azimuth compression on the pretreated echo signal data based on the two-dimensional space-varying phase errors to obtain focused imaging results.

The invention provides a gradient-based black box face deep counterfeiting watermarking resisting method, equipment and a medium, and relates to the technical field of image processing. The method comprises the following steps: acquiring an original face image, and inputting the original face image into a forward noise adding process of a denoising diffusion implicit model to obtain a noise potential variable in the step; and taking the variable as an initial denoising starting point for resisting watermark generation, executing a reverse denoising process of the denoising diffusion implicit model, and estimating a loss gradient corresponding to the depth forgery model under the setting of a black box by adopting a gradient estimation method based on a natural evolution strategy in each denoising process. And weighting the loss gradient and a preset guide weight, and then superposing the weighted weight to the denoised image in the current denoising step to generate an intermediate confrontation face image in the current denoising step. And continuously iterating the middle confrontation face image based on each de-noising step until all de-noising steps are completed, and obtaining a final confrontation face image.

The invention provides a model generation method and device, a marketing text generation method and device and network device.The model generation method for generating marketing texts comprises the steps that historical marketing texts are obtained, and a training data set is generated; performing noise addition processing on original data in the training data set to generate first data; according to the dominant function, diffusion denoising processing is carried out on the first data step by step through a diffusion model, in the denoising processing process, the diffusion model is updated based on gradient calculation until convergence is achieved every a first number of diffusion steps, and a target model used for generating a marketing text is obtained, the diffusion model is used for carrying out denoising processing on the first data according to the strategy network, and in each diffusion step, the dominant function is used for reducing gradient estimation variance of strategy network parameters by evaluating relative advantages of denoising actions in a current state. The marketing text generated by adopting the target model is high in accuracy and high in adaptability, so that the marketing effect is remarkable.

The invention relates to a switchable activation network reasoning method and device based on dynamic gating and a medium. The method comprises the following steps: firstly, inputting input data in a training data set into a first neural network, and calculating a first activation result through a learnable soft gating function; then, in combination with a label corresponding to the first activation result, a through gradient estimator is adopted, a preset loss function is minimized through back propagation, and a second neural network is obtained; the preset loss function comprises a target loss function and a multi-dimensional constraint, so that the second neural network is balanced between precision and efficiency. Then, processing the second neural network based on a hard gating function inheriting gating parameters of the soft gating function to obtain a third neural network; and inputting to-be-processed test data into the third neural network, and outputting a prediction result corresponding to the test data. Therefore, the balance between the efficiency and the precision can be realized when the deep neural network performs efficiency optimization.

The invention relates to a distributed database parameter adaptive tuning method based on multi-agent deep reinforcement learning, and belongs to the technical field of information. According to the method, the thought of a multi-agent deep reinforcement learning algorithm is introduced into the field of database parameter tuning, the cooperation and competition relation between nodes in a distributed database environment is explored, and a deep deterministic strategy gradient reinforcement learning algorithm C-MADDPG based on a centralized strategy gradient estimator is provided. A distributed database parameter tuning problem is modeled based on a partially observable Markov decision process. Problem definition takes expansion of a parameter search space as a cost, takes a complex competition effect between database nodes as a black box, carries out mathematical modeling on an observable cooperation effect, improves the universality and scalability of an algorithm, solves a relative generalization problem of the algorithm, and can be expanded to a general distributed database architecture. The C-MADDPG provided by the invention shows good performance in the parameter tuning of the distributed database.

The invention discloses a hovercraft and a parameter integrated design method, device and equipment thereof, and the method comprises the steps: fixing the basic structure parameters of a propeller of the hovercraft, and randomly sampling the strategy hyper-parameters of different controllers on the basis of the basic structure parameters; executing the navigation task in the simulation environment based on different performance costs to obtain corresponding performance costs; a self-adaptive optimization method based on historical gradient estimation is adopted to analyze the variation trend with the system performance, and iterative updating is carried out according to the variation trend until the performance cost numerical value is converged, so that an optimal strategy hyper-parameter is obtained; fixing of the basic structure parameters is relieved, the basic structure parameters and the basic structure parameters jointly form a design vector, the optimal strategy hyper-parameters serve as the benchmark, a two-stage Bayesian optimization strategy is adopted to conduct collaborative search on the design vector, and a global optimal design vector is obtained; and carrying out integrated design of the hovercraft based on the optimal design vector.

According to one aspect of the present disclosure, a method of image processing and a computer-readable medium are provided. The method may include: inputting a first color image and a first depth image into a gradient-estimation network, performing gradient-estimation of the first color image and the first depth image using the gradient-estimation network to generate first depth-edge information, inputting a second depth image and the first depth-edge information into a depth-upsampling network, performing depth upsampling of the second depth image using the first depth-edge information to generate second depth-edge information, inputting the first depth-edge information and the second depth-edge information into a fusion network, fusing the first depth-edge information and second depth-edge information using the fusion network to generate a residual map, and combining the first depth image and the residual map to generate a third depth image.

The invention discloses a prediction and decision-making integrated resource scheduling method and system for an electricity-hydrogen-heat comprehensive energy system. The method comprises the following steps: establishing an electricity-hydrogen-heat comprehensive energy system resource scheduling optimization model; constructing a prediction network of uncertain parameters required by the resource scheduling optimization model, and predicting future photovoltaic output and load demands by using historical multi-day data in a sliding window mode; respectively inputting the predicted data and the real data into a solver to solve a scheduling problem, and constructing a decision-oriented loss function by comparing the operating cost differences of the predicted data and the real data; a random disturbance gradient estimation method is adopted to calculate the gradient of the loss function to the predicted network parameters, and a back propagation algorithm is utilized to iteratively update the network parameters; and predicting a future scene by using the trained prediction network, and inputting a prediction result into a solver to obtain an optimal scheduling scheme and minimum operation cost. Compared with a traditional method, the method has the advantage that the daily operation cost can be reduced by 0.90%-6.30%.

According to one aspect of the present disclosure, an image processing method is provided. The method may include performing gradient estimation on a first color image and a first depth image using a gradient estimation network to generate first depth edge information. The method may include inputting the second depth image and the first depth edge information into a depth upsampling network. The method may include performing depth upsampling on the second depth image using the first depth edge information to generate second depth edge information. The method may include inputting the first depth edge information and the second depth edge information into a convergence network that fuses the first depth edge information and the second depth edge information to generate a residual map. The method may include merging the first depth image and the residual map to generate a third depth image.

The application designs a natural evolution strategy optimization method based on variance reduction technology, aiming at solving the problem of large gradient estimation variance and slow convergence speed in traditional natural evolution strategy. The method combines variance reduction technology, introduces global average gradient and small batch gradient correction in the optimization process, significantly reduces the variance of gradient estimation, improves the optimization accuracy and efficiency. Specifically, the method includes the following steps: first, initialize the optimization parameters, including the initial solution, learning rate and step size; then calculate the global gradient by input data, which is used for subsequent correction; in the inner loop, calculate the objective function value and gradient for small batch perturbation samples, and combine the global gradient for variance correction to update the optimization parameters. Compared with the traditional method, the application has the advantages of high gradient estimation accuracy and fast convergence speed, and is suitable for black box objective function optimization scenarios, and has wide application value in the field of machine learning model training.

The application provides a gradient-based black-box face deepfake adversarial watermarking method, device and medium, and relates to the technical field of image processing. The method comprises the following steps: obtaining an original face image, inputting the original face image into a forward noise adding process of a denoising diffusion implicit model, and obtaining a noise latent variable of the first step. The variable is used as an initial denoising starting point for adversarial watermark generation, a reverse denoising process of the denoising diffusion implicit model is performed, a gradient estimation method based on a natural evolution strategy is used in each denoising process, and a loss gradient corresponding to a deepfake model is estimated under a black-box setting. The loss gradient is weighted with a preset guide weight, and then superimposed on an image after denoising of the current denoising step to generate an intermediate adversarial face image of the current denoising step. The intermediate adversarial face images of each denoising step are continuously iterated until all denoising steps are completed, and a final adversarial face image is obtained.

The application relates to the technical field of data processing, in particular to a radio frequency matching parameter real-time optimization method based on gradient descent, a digital measurement data set is acquired, and performance index statistical measurement values are included; based on the digital measurement data set, gradient estimation values of to-be-optimized matching parameters in a target cost function are calculated; the gradient estimation values are processed through a data processing gradient estimation algorithm, and optimized matching parameters are obtained; a disturbance quantity matrix is applied to the matching parameters, performance index statistical measurement value matrices are acquired, data-driven gradient estimation values are obtained; prediction gradient information is calculated through a statistical approximation model based on the performance index statistical measurement values; the prediction gradient information and the data-driven gradient estimation values are subjected to data fusion processing, and first gradient estimation values are generated; the currently calculated first gradient estimation values are subjected to time sequence data processing, and optimal gradient estimation values are obtained; and optimization matching parameters of a next optimization iteration cycle are generated based on a probability density function.

The invention discloses a geologic modeling data spatial interpolation method based on anisotropic Huber robust reweighting, and the method comprises the steps: obtaining stratigraphic scatter data, obtaining a stratigraphic elevation gradient through local neighborhood construction and gradient estimation, expanding the stratigraphic elevation gradient into a continuous gradient field, and constructing a trend-inclination direction field; selecting neighborhood sample points of the query points, projecting the neighborhood sample points to a constructed coordinate system, and defining an anisotropic distance to construct a space kernel weight coefficient; after initial weighted least square fitting, a Huber robust reweighting strategy is introduced, the comprehensive weight is optimized through residual segmentation processing, and finally an interpolation result is obtained through refitting. The method breaks through the traditional isotropic limitation, effectively inhibits outlier and noise interference, does not need an artificial prior geological model, maintains high stability and high precision in a complex scene, and provides reliable data support for geological modeling.

The application relates to a noise reduction system and method based on a sequence pipeline transposed RDFxLMS, wherein a FIR filter and a secondary path adopt a transposed form, the key path in the algorithm structure is short, and the clock speed of the system can be greatly improved. In the algorithm, an input signal is filtered through a FIR filter module to obtain a filter output. An error calculation module mainly comprises a transposed FIR filter and a subtractor, and is used for calculating an error signal between the filter output and an expected output. A weight value updating module calculates new weight values according to the error signal and the filter input, and stores the new weight values in a weight value memory. A secondary path module is used for correcting an error gradient estimation value of the LMS algorithm, so that the convergence performance of the filter is improved. A secondary path output is calculated according to the new weight values and the filter input, and the secondary path output is added to a main path output to obtain a final output signal. The secondary path output signal is used for correcting the weight values of the main path, so that the noise reduction effect is improved.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a semi-asynchronous federal learning method and device based on poisoning attack defense and a storage medium, and the method comprises the steps: in any training round, a server receives a first preset number of local models arriving at first; grouping the local models based on the old degrees of the local models; screening out candidate local models from the local models in each group, and carrying out intra-group model aggregation to obtain a group representative model corresponding to each group; determining an equivalent local gradient of each group of representative models based on each group of representative models, a global model obtained in the previous training round and an equivalent global gradient of the global model, estimating the equivalent global gradient of the training round, determining candidate group representative models and inter-group aggregation weights of the candidate group representative models based on the equivalent local gradient, and executing inter-group aggregation to obtain a candidate group representative model; and determining a global model obtained in the training round, thereby realizing the poisoning attack defense of semi-asynchronous federal learning.

This invention discloses a method, apparatus, terminal, and medium for distributed bi-level optimization on time-varying directed graphs, comprising: acquiring a time-varying directed graph sequence; solving a bi-level optimization problem for a multi-agent system based on the time-varying directed graph sequence; updating the decision variables of each agent using a row random matrix and calculating the local gradient of the decision variables of each agent using a penalty function; updating the gradient tracking variables of each agent using a column random matrix to eliminate gradient estimation bias in the time-varying directed graph sequence; and outputting the bi-level optimization results for the multi-agent system. This invention solves the problem of bi-level optimization failure under dynamic topology, eliminates the risk of numerical instability, overcomes the second-order computational bottleneck, and reduces resource overhead.

The application relates to a logistics AGV formation cooperative control method based on a DMG-MPC algorithm, which comprises the following steps of defining initialization parameters, constructing a model, solving optimal temporary variables by using estimated gradients, updating local variables of a current node and projecting in combination with neighbor nodes, updating auxiliary variables, obtaining the gradient of the current node by updating a gradient estimator, designing an iterative control algorithm and performing inner and outer double-layer iterations. By adopting a double-layer structure, the non-convex cooperative optimization problem constructed in a multi-AGV system is solved while the feasibility and calculation efficiency of distributed solving are ensured, the momentum method is combined with the gradient tracking method, a faster convergence rate is obtained, the projection operation is adopted to strictly guarantee the feasibility of AGV dynamics constraints, a plurality of AGVs can realize full autonomous cooperative navigation and dynamic obstacle avoidance in a warehouse environment, in an emergency working condition such as a device fault or a passage blockage scene, transportation tasks are re-distributed and a cooperative bypass path is generated, and the overall loading and unloading efficiency is improved.

The invention belongs to the field of artificial intelligence and machine learning, particularly relates to a credit score card construction method, system and device and a storage medium, and aims to solve the problems that an existing credit evaluation model is difficult to process high-dimensional heterogeneous data and neural network training is unstable. The method comprises the steps of performing preprocessing and feature screening on multi-source heterogeneous credit data, and generating an initial population by adopting chaotic mapping improved by designing an adaptive disturbance strategy so as to improve diversity and uniformity during population initialization and optimize initial parameters of a neural network; a gradient estimation deviation correction mechanism is introduced, gradient noise interference in the training process is suppressed, and the convergence stability of the model is improved; and finally, the output of the neural network is converted into interpretable credit scores and risk levels. The method effectively solves the problems that when a traditional credit evaluation model processes high-dimensional heterogeneous data, the feature extraction capacity is insufficient, an optimization algorithm is prone to premature convergence, and the training process is unstable.

This invention discloses an adaptive distributed support vector regression method to combat Byzantine faults. First, the objective function of the SVR model is smoothed to construct an empirical risk minimization objective function. Then, with t=1, the master machine obtains initial parameter estimates on its local data. In the t-th iteration, a MOM-based aggregation method is used to obtain the MOM estimate, which is then used as the global gradient estimate. Subsequently, a robust global gradient is obtained based on the global gradient estimate. After obtaining the robust global gradient, the master machine updates the global parameters using gradient descent. Finally, it checks whether the convergence condition is met. If the convergence condition is not met, the above steps are repeated; otherwise, the globally optimal parameter estimate is obtained. By introducing a robust aggregation mechanism based on the MOM method, it can effectively suppress the influence of abnormal machines, significantly improving the stability and robustness of the system while ensuring prediction accuracy. It can be widely applied to various practical distributed systems.